CCATPREPARATION AI Module 2

Intelligent System
Architecture of learning agent. [ V Imp]
Learning Agent :
A learning agent in AI is the type of agent that can learn from its past experiences or it has
learning capabilities. It starts to act with basic knowledge and then is able to act and adapt
automatically through learning.
A learning agent has mainly four conceptual components, which are:
1. Learning element: It is responsible for making improvements by learning from the

environment
2. Critic: The learning element takes feedback from critics which describes how well the
agent is doing with respect to a fixed performance standard.
3. Performance element: It is responsible for selecting external action
4. Problem Generator: This component is responsible for suggesting actions that will lead to
new and informative experiences.
A learning agent has mainly four conceptual components, which are:

1. Learning element: It is responsible for making improvements by learning from the
environment
2. Critic: The learning element takes feedback from critics which describes how well the
agent is doing with respect to a fixed performance standard.
3. Performance element: It is responsible for selecting external action
Join Our Telegram Group to Get Notifications, Study Materials, Practice test & quiz: https://t.me/ccatpreparations
Visit: www.ccatpreparation.com
4. Problem Generator: This component is responsible for suggesting actions that will lead to
new and informative experiences.
Describe each of learning component w.r.t. Medical diagnosis system

In the context of a medical diagnosis system, the components of a learning agent can be defined
as follows:
1. Environment: The environment in this case would be the medical field, which includes
various diseases, symptoms, medical tests, treatments, and patient data.
2. Sensors: The sensors in a medical diagnosis system would include data from various sources,
such as medical records, laboratory test results, patient history, and medical imaging data.
3. Learning Algorithms: [ This is a Combination of Critics , Learning Element and Problem

generator ]
The learning algorithms in a medical diagnosis system would be used to analyze the data from
the sensors and identify patterns and relationships that can be used to diagnose diseases. These
algorithms can include machine learning techniques such as decision trees, neural networks, and
support vector machines.
4. Actuators: In a medical diagnosis system, the actuators would be the output of the system,
which could include a diagnosis, a treatment plan, or a referral to a specialist.
Here's how each component would work in a medical diagnosis system:
1. Environment: The environment would provide the data for the medical diagnosis system.
This data would include information about various diseases, their symptoms, the results of
medical tests, and patient data.
2. Sensors: The sensors would collect data from various sources, such as medical records,
laboratory test results, patient history, and medical imaging data. This data would be used as
input for the learning algorithms.
3. Learning Algorithms: The learning algorithms would analyze the data from the sensors and
identify patterns and relationships that can be used to diagnose diseases. For example, if a patient
has a particular combination of symptoms and test results, the learning algorithm could identify a
particular disease that is likely to be the cause.
4. Actuators: The actuator in a medical diagnosis system would be the output of the system.
This could include a diagnosis, a treatment plan, or a referral to a specialist. The output would be
based on the analysis of the data by the learning algorithms.
Overall, the learning components of a medical diagnosis system work together to analyse patient
data and provide an accurate diagnosis based on the available information. As the system learns
from new data, it can improve its accuracy and provide better diagnoses over time
List Down all the types of Agent Explain Each with a block diagram. [ V Imp ]
Agents can be grouped into four classes based on their degree of perceived intelligence and
capability:
● Simple Reflex Agents
● Model-Based Reflex Agents
● Goal-Based Agents
● Utility-Based Agents
Simple Reflex Agent:
● This agent works only on the basis of current perception and it does not bother about
the history or previous state in which the system was.
● This type of agent is based upon the condition-action rule. If the condition is true,
then the action is taken, else not.
PROBLEMS FACED:
1. Very limited intelligence.

2. No knowledge about the non-perceptual parts of the state.
3. Operating in a partially observable environment, infinite loops are unavoidable.
Model based reflex agents

● It works by finding a rule whose condition matches the current situation.
● It can handle partially observable environments.
● Updating the state requires information about how the world evolves independently from
the agent and how the agent actions affect the world.
Goal based reflex agents
●The goal-based agent focuses only on reaching the goal set and hence the decision took
by the agent is based on how far it is currently from their goal or desired state.
● Their every action is intended to minimize their distance from the goal.
● This agent is more flexible, and the agent develops its decision-making skill by choosing
the right from the various options available.
Utility based agents
● These agents are more concerned about the preference(utility) for each state. When there
are multiple options available, the utility-based agent takes the decision on the basis that
how much satisfaction the agent gets from it.
● This approach was like somewhat adding emotions to the agent, because, after taking any
decision, the agent ensures that "how happy I Am after taking this decision?".
● This agent was developed because sometimes achieving the desired goal is not enough.
We may look for quicker, safer and cheaper alternate to reach the destination.
Compare Model Based, Goal based and Utility Based Agent
Differentiate Between Informed Search and Uninformed Search Algorithm
Compare Problem solving and Planning Agent
Overall problem-solving agents and planning agents have different approaches and
requirements, and are suitable for different types of tasks.
● Problem-solving agents are focused on finding a solution to a specific problem using

search algorithms to find a sequence of actions.
● Planning agents are focused on generating a sequence of actions that will achieve a goal
using symbolic manipulation to generate a plan.
● The choice of agent type will depend on the specific requirements of the task and the
nature of the problem domain

CCATPREPARATION AI Module 2

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CCATPREPARATION AI Module 2

Uploaded by

Copyright:

Available Formats

Intelligent System

Architecture of learning agent. [ V Imp]

A learning agent has mainly four conceptual components, which are:

1. Learning element: It is responsible for making improvements by learning from the

3. Performance element: It is responsible for selecting external action

A learning agent has mainly four conceptual components, which are:

Describe each of learning component w.r.t. Medical diagnosis system

3. Learning Algorithms: [ This is a Combination of Critics , Learning Element and Problem

1. Very limited intelligence.

Model based reflex agents

● It can handle partially observable environments.

Compare Model Based, Goal based and Utility Based Agent

● Problem-solving agents are focused on finding a solution to a specific problem using

You might also like